KR102515439B1 - Method, device and system for matching beauty product manufacturers using influencer information and brand maker information based on artificial intelligence - Google Patents

Abstract

A device according to an embodiment: obtains information on a first product, which is a beauty product to be developed, from a brand maker terminal and the plan of the first product; obtains the category of the first product based on the information on the first product; obtains information on a second product, which is a beauty product in the same category as the category of the first product and has a sales volume equal to or greater than a reference value, among products manufactured by a beauty product manufacturer from a database; matching a brand maker with the beauty product manufacturer based on the information on the second product; obtains advertisement content performed by an influencer from at least one database; obtains the advertisement information of a candidate influencer having advertisement content related to beauty products accounting for a preset reference proportion or more of all advertisement content based on the advertisement content performed by the influencer; obtains information on the advertisement content performed by the candidate influencer based on the advertisement information of the candidate influencer; and selecting an influencer to perform the advertisement of the first product among candidate influencers based on the advertisement information of the candidate influencer, the information on the advertisement content performed by the candidate influencer, and information on the first product.

Description

Beauty product manufacturer matching method, device, and system using artificial intelligence-based influencer information and brand maker information

The following embodiments relate to a beauty product manufacturer matching method, device, and system using artificial intelligence-based influencer information and brand maker information.

Modern consumers have more individual tendencies than in the past, and the trend toward well-being is especially prominent. Therefore, a new concept market cannot be formed with one-size-fits-all products, and an approach that can accurately reflect the characteristics of each customer is needed.

However, in the conventional beauty product manufacturing system, it is difficult to select and manufacture beauty products desired by consumers, and in the case of brand makers, a real-time collaboration system does not exist, so it takes considerable time to develop and produce new products.

Influencer is a term that refers to a person with high social influence. It refers to an individual blogger or SNS user who has hundreds or dozens of followers. With the recent development of the Internet, the influence of influencers on society is increasing. .

Due to this, companies are marketing their products through influencers, and in line with this situation, development of platforms that connect companies and influencers is continuing.

Therefore, research on the process of matching beauty product manufacturers using influencer information and brand maker information is required.

Korean Patent Registration No. 10-2270645 Korean Registered Patent No. 10-2278809 Korean Patent Publication No. 10-2022-0051501 Korean Patent Publication No. 10-2022-0053131

Embodiments try to select a beauty product manufacturer and an influencer based on the beauty product that the brand maker wants to develop.

In the embodiments, a reliability index is generated through the number of products of beauty product manufacturers, and a recommendation index is generated through the sales volume of products to perform matching between a brand maker and a beauty product manufacturer.

In the embodiments, the target information of the influencer and the content interest information of the influencer are acquired, and the obtained information is applied to an artificial neural network to match the influencer and the product.

A beauty product manufacturer matching method using artificial intelligence-based influencer information and brand maker information includes acquiring information on a first product, which is a beauty product to be developed, and a proposal for the first product, from a brand maker terminal; obtaining a category of the first product based on the information of the first product; acquiring, from a database, information on a second product among products manufactured by the beauty product manufacturer, the sales quantity of which is equal to or greater than a reference value, and which is a beauty product whose category is the same as that of the first product; performing matching between the brand maker and the beauty product manufacturer based on the second product information; Obtaining advertising content performed by an influencer from at least one database; Obtaining advertisement information of a candidate influencer whose ratio of advertisement contents related to beauty products among all advertisement contents is equal to or greater than a preset reference ratio, based on the advertisement contents performed by the influencer; obtaining advertisement content information performed by the candidate influencer based on the advertisement information of the candidate influencer; and an influencer who will perform an advertisement for the first product among the candidate influencers based on the advertisement information of the candidate influencer, the advertisement content information performed by the candidate influencer, and the information of the first product. It includes the step of selecting a word.

The matching of the brand maker and the beauty product manufacturer based on the information of the second product may include obtaining the number of the second products of the beauty product manufacturer; generating a trust index of the beauty product manufacturer based on the number of the second products; Based on the information on the second product, products whose actual sales volume of the product among the second products is greater than a predefined expected sales volume are classified into a first group, and the actual sales volume of the product among the second products is the expected sales volume. classifying products that are no larger than a second population; generating a first number that is the number of products classified into the first group; generating a second number that is the number of products classified into the second group; generating a third number that is a sum of the first number and the second number; generating a recommendation index of the beauty product manufacturer based on a value obtained by dividing the first number by the third number; generating a score of the beauty product manufacturer based on a trust index of the beauty product manufacturer and a recommendation index of the beauty product manufacturer; and performing matching between the brand maker and the beauty product manufacturer based on the score of the beauty product manufacturer.

Selecting an influencer to advertise the first product from among the candidate influencers includes target age information and target gender information of the candidate influencer based on the information of the candidate influencer obtaining target information of the candidate influencer; The candidate influencer including the number of advertisement contents, the average number of views of the advertisement contents, the average number of advertisement sharing of the contents, and the average number of comments on the advertisement contents, based on the advertisement contents information of the candidate influencer. obtaining content interest information of; generating a first input signal based on target information of the candidate influencer, content interest information of the candidate influencer, and information of the first product; generating a first output signal by applying the first input signal to a first artificial neural network; generating matching information corresponding to the first product and the candidate influencer based on the first output signal; checking a history of advertising products produced by a matched beauty product manufacturer among the candidate influencers and applying a weight proportional to the number of advertisements to the matching information; and selecting an influencer to advertise the first product using the weighted matching information.

The step of analyzing the advertising contribution of the first product through the selected influencer is further included, and the step of analyzing the advertising contribution of the first product through the selected influencer is the step of analyzing the first product from the brand maker terminal. obtaining a release time of product 1, an upload time of advertisement content of the first product, and a posting maintenance period, and transmitting the acquired information to the terminal of the selected influencer; generating a first period from the time of release of the first product to the time of uploading advertisement contents of the first product; generating a first sales volume that is the sales volume of the first product during the first period; setting a reference range based on the first sales amount; generating a second sales volume, which is a sales volume during the first period from a release time of a third product matching the category of the first product among products released by the brand maker; checking whether the second sales volume is within the reference range, and classifying third products having the second sales volume within the reference range into groups; generating a second period from a release time of the first product to a time when a preset period elapses after uploading advertisement content of the first product; generating a first total sales volume that is the total sales volume of the first product during the second period; generating a second overall sales volume by calculating an average value sold during the second period from the release time of the third product included in the group; determining whether the first total sales amount is greater than the second total sales amount; if it is determined that the first total sales amount is greater than the second total sales amount, determining that there is an advertising contribution of the first product through the influencer; and if it is determined that the first total sales amount is not greater than the second total sales amount, it is determined that the advertising contribution of the first product through the influencer is insufficient, and the advertisement content of the first product and the first product Monitoring sales volume, and generating a report on the monitoring.

A beauty product manufacturer matching method using artificial intelligence-based influencer information and brand maker information includes acquiring information on all contents uploaded by the selected influencer; Among all contents uploaded by the selected influencers, contents including advertising contents are classified as the first group, and among all contents uploaded by the selected influencers, contents that do not include advertisement contents are classified as the second group. classifying; acquiring advertising content running times corresponding to the content included in the first meeting, calculating an average value of the advertising content running times, and generating the first time; generating a first average number of views by analyzing the number of views corresponding to the content included in the first meeting; generating a second average number of views by analyzing the number of views corresponding to the content included in the second meeting; generating a first ratio by dividing the first average number of hits by the second average number of hits; determining whether the first ratio is greater than 1; If it is determined that the first ratio is greater than 1, generating advertisement content for the first product for a second time period longer than the first time period and providing the advertisement content to the terminal of the selected influencer; if it is determined that the first ratio is not greater than 1, determining whether the first ratio is greater than a predefined first reference ratio; If it is determined that the first ratio is greater than the first reference ratio, generating advertisement content for the first product for the first time and providing the advertisement content to the selected influencer terminal; and if it is determined that the first ratio is not greater than the first reference ratio, generating advertisement content for the first product in a third time shorter than the first time and providing the advertisement content to the terminal of the selected influencer. more includes

A beauty product manufacturer matching method using artificial intelligence-based influencer information and brand maker information includes: extracting a video image of a first view from the advertisement content as a first image when the advertisement content is uploaded to a video sharing site; dividing an area occupied by the advertisement-related product into a first area in the first image, and extracting a 1-1 image by dividing a portion of the first image where the first area is located; dividing an area occupied by the influencer in the 1-1 image into a second area when it is determined that the influencer is present in the 1-1 image; As a result of reproducing and analyzing the advertising content in reverse chronological order from the first point of view, if it is confirmed that the influencer is not present in the second area at the second point of view, the video image of the second point of view is displayed in the advertising content. 2 Extracting as an image; extracting a 2-1 image by dividing a portion of the second image in which the second area is located; replacing a portion of the 1-1 image with the second area with the 2-1 image; and adding and registering the 1-1 image as an image of the advertisement-related product on the first page.

An apparatus according to an embodiment may be combined with hardware and controlled by a computer program stored in a medium to execute any one of the methods described above.

In embodiments, a beauty product manufacturer and an influencer may be selected based on a beauty product that the brand maker intends to develop.

According to embodiments, a reliability index is generated through the number of products of beauty product manufacturers, and a recommendation index is generated through the sales volume of products to perform matching between brand makers and beauty product manufacturers.

Embodiments may acquire influencer target information and influencer content interest information, and apply the acquired information to an artificial neural network to match influencers and products.

On the other hand, the effects according to the embodiments are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a diagram schematically showing the configuration of a system according to an embodiment.
2 is a flowchart illustrating a process of matching a beauty product manufacturer and an influencer through a beauty product that a brand maker intends to develop according to an embodiment.
3 is a flowchart illustrating a process of matching a beauty product manufacturer and a brand maker through performance results of the beauty product manufacturer according to an embodiment.
FIG. 4 is a diagram for explaining a process of selecting an influencer to advertise a product based on information on candidate influencers according to an embodiment.
5 is a flowchart illustrating a process of determining an advertisement contribution when a selected influencer performs an advertisement according to an embodiment.
6 is a flowchart illustrating a process of providing product information to a selected influencer according to an embodiment.
7 is a flowchart illustrating a process of replacing an image including an influencer with a product image on a sales page according to an embodiment.
8 is an exemplary diagram of a configuration of a device according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes can be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents or substitutes to the embodiments are included within the scope of rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only, and may be modified and implemented in various forms. Therefore, the embodiments are not limited to the specific disclosed form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Although terms such as first or second may be used to describe various components, such terms should only be construed for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

It should be understood that when an element is referred to as being “connected” to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle.

Terms used in the examples are used only for descriptive purposes and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

In addition, in the description with reference to the accompanying drawings, the same reference numerals are given to the same components regardless of reference numerals, and overlapping descriptions thereof will be omitted. In describing the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description will be omitted.

The embodiments may be implemented in various types of products such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent vehicles, kiosks, and wearable devices.

1 is a diagram schematically showing the configuration of a system according to an embodiment.

Referring to FIG. 1 , a system according to an embodiment may include a brand maker terminal 100, a beauty product manufacturer terminal 300, an influencer terminal 400, and a device 200 capable of communicating with each other through a communication network. can

First, a communication network may be configured regardless of its communication mode, such as wired or wireless, and may be implemented in various forms so that communication between servers and communication between servers and terminals is performed.

The brand maker terminal 100 has information about ideas for beauty products, but it is difficult to manufacture beauty products or advertise directly, so it produces beauty products through beauty product manufacturers and advertises beauty products through influencers. As a terminal used by a user who wants to perform, it may be a desktop computer, a laptop computer, a tablet, a smart phone, and the like. For example, as shown in FIG. 1 , the brand maker terminal 100 may be a smart phone and may be employed differently depending on embodiments.

The beauty product manufacturer terminal 300 is a terminal used by a user who directly manufactures beauty products, including cosmetic contents and cosmetic containers, and may be a desktop computer, a laptop computer, a tablet computer, a smart phone, and the like. For example, as shown in FIG. 1 , the beauty product manufacturer terminal 300 may be a smart phone or may be employed differently depending on embodiments.

An influencer is a user who is active through social network services (SNS), has followers and influence, and is a user who creates and uploads content advertising beauty products to advertise beauty products. The influencer's terminal 400 is a terminal used by the influencer, and may be a desktop computer, laptop, tablet, smartphone, and the like. For example, as shown in FIG. 1 , the influencer's terminal 400 may be a smart phone or may be employed differently depending on the embodiment.

Each of the brand maker terminal 100, the beauty product manufacturer terminal 300, and the influencer terminal 400 is configured to perform all or part of the calculation function, storage/reference function, input/output function, and control function of a normal computer. It can be. The brand maker terminal 100 , the beauty product manufacturer terminal 300 , and the influencer terminal 400 may be configured to communicate with the device 200 in a wired or wireless manner.

Each of the brand maker terminal 100, the beauty product manufacturer terminal 300, and the influencer terminal 400 uses the device 200 to access a website operated by a service provider or organization, or the device ( 200), applications developed and distributed by service providers or organizations can be installed. Each of the brand maker terminal 100, the beauty product manufacturer terminal 300, and the influencer terminal 400 may be linked with the device 200 through a website or an application.

In FIG. 1 and the following description, for convenience of explanation, only one brand maker terminal 100, a beauty product manufacturer terminal 300, and an influencer terminal 400 are shown and described, but the number of terminals depends on the embodiment. can vary depending on As long as the processing capacity of the device 200 allows, the number of terminals is not particularly limited.

The device 200 may be a server owned by a person or organization that provides services using the device 200, may be a cloud server, or may be a peer-to-peer (p2p) set of distributed nodes. may be The device 200 may be configured to perform all or some of the arithmetic function, storage/reference function, input/output function, and control function of a normal computer. The device 200 may include at least one artificial neural network that performs an inference function. The device 200 may be configured to communicate with the brand maker terminal 100 , the beauty product manufacturer terminal 300 , and the influencer terminal 400 through wired or wireless communication.

The device 200 may select a beauty product manufacturer and an influencer based on a beauty product that the brand maker wants to develop.

2 is a flowchart illustrating a process of matching a beauty product manufacturer and an influencer through a beauty product that a brand maker intends to develop according to an embodiment.

Referring to FIG. 2 , first, in step S201 , the device 200 may obtain information on a first product, which is a beauty product to be developed, and a proposal for the first product from the brand maker terminal. In this case, the information on the first product may include a name of the first product, a category of the first product, information on ingredients of the first product, and the like, and the proposal of the first product includes information on the first product, and It may include the quantity of the product, the expected cost of the first product, the expected delivery date of the first product, and the like.

Specifically, the device 200 includes the name of the first product, which is a beauty product to be developed from the brand maker terminal, the category of the first product, information on the first product including component information of the first product, the quantity of the first product, A proposal for the first product including an estimated cost of the first product and an estimated delivery date of the first product may be obtained.

In step S202, the device 200 may obtain a category of the first product based on the information of the first product. In this case, the category may include basic cosmetics, color cosmetics, hair and body, perfume and detergent, and other categories.

For example, when the first product is shampoo, the device 200 may obtain a category of the first product as hair and body based on information on the first product.

In operation S203 , the device 200 may obtain information on a second product among products manufactured by a beauty product manufacturer, the sales quantity of which is equal to or greater than a reference value, and which is a beauty product whose category is the same as that of the first product, from the database. Here, the reference value is a preset value and may vary according to embodiments. Also, there may be one second product or a plurality of second products. In addition, the sales quantity may be the sales quantity from the release date of the product to the present, the sales quantity for 6 months from the release date of the product, or the sales quantity for 1 year from the release date of the product. It may also be the number of sales up to a preset period other than that.

Specifically, the device 200 may store information related to the beauty product manufacturer in the database, and among the products manufactured by the beauty product manufacturer stored through the database, the sales quantity is equal to or greater than a reference value, and the category is the same as that of the first product. Information on a second product that is the same beauty product may be obtained.

Also, the device 200 may obtain information related to the beauty product manufacturer through the beauty product manufacturer terminal 300 .

For example, if the category of the first product is hair and body, information on 'A' beauty product manufacturer, 'B' beauty product manufacturer, and 'C beauty product manufacturer' is stored in the database, and 'A' beauty product manufacturer 'A' beauty product manufactured has sales of 8,000,000 units, category is hair and body, 'B' beauty product manufactured by 'B' beauty product manufacturer has sales of 4,000,000 units, category is hair and body, ' If the number of 'C' beauty products manufactured by the manufacturer C' beauty products is 6,000,000 units, the category is color cosmetics, and the reference value of the number of units sold is 5,000,000 units, the device 200 operates the 'A' beauty product manufacturer stored in the database. , 'B' beauty product manufacturer and 'C beauty product manufacturer's information, 'A' beauty product manufacturer's sales quantity is 8,000,000 units, and 'A' beauty product whose category is hair and body can be extracted, ' Information on A' beauty products can be acquired.

In step S204, the device 200 may match the brand maker with the beauty product manufacturer based on the second product information.

Specifically, the device 200 may perform matching between the brand maker and the beauty product manufacturer through the number of second products corresponding to the beauty product manufacturer and the sales volume of the second product. In this regard, a detailed description will be made with reference to FIG. 3 .

In step S205, the device 200 may obtain advertising content performed by the influencer from at least one database. Here, at least one database may be a blog or YouTube.

Specifically, the device 200 may obtain advertising content performed by an influencer through at least one database including a blog or YouTube.

In step S206, the device 200 acquires advertisement information of a candidate influencer whose ratio of advertisement contents related to beauty products among all advertisement contents is equal to or greater than a preset reference ratio, based on the advertisement contents performed by the influencer. can do. Here, the reference ratio is a preset ratio and may vary according to embodiments. In addition, the advertisement information of the candidate influencer may include information about the candidate influencer including the name of the candidate influencer, the followers of the candidate influencer, and the information on the followers of the candidate influencer. It may include information on the advertisement content performed by the candidate influencer, including the number of advertisement contents of the influencer, the category of advertisement contents of the candidate influencer, the number of views, the number of comments, and the number of shares of the candidate influencer's advertisement contents. there is.

Specifically, the device 200 classifies the advertising content corresponding to the influencer based on the advertising content performed by the influencer, and analyzes the product of the advertising content to determine whether the advertising content is related to a beauty product or not. It is possible to analyze whether advertisement content is not related to beauty products. That is, the device 200 may check the ratio of advertisement content related to beauty products among all advertisement contents based on the advertisement contents performed by the influencer, and the candidate influencer whose ratio is equal to or greater than the preset reference ratio. of advertisement information can be obtained.

For example, through at least one database, the YouTube database, 'A' advertisement content, 'B' advertisement content, 'C' advertisement content, 'D' advertisement content, 'E' advertisement content, 'F' advertisement content, ' Acquire G' advertising content, "H" advertising content, "I" advertising content, and "J" advertising content, and the advertising content corresponding to the 'A' influencer is 'A' advertising content for beauty products, 'D' advertisement content for beauty products, 'B' advertisement content for food, 'F' advertisement content for beauty products, and 'B' advertisement content for food. 'I' is advertising content, 'C' is advertising content corresponding to influencers, 'C' advertising content for beauty products, 'E' advertising content for beauty products, and clothing advertisements 'G' advertisement content as content, 'H' advertisement content as beauty product advertisement content, and 'J' advertisement content as beauty product advertisement content, and the reference ratio is 75%, the device 200 stores at least one database Through the in-YouTube database, 'A' influencers and 'C' influencers whose advertising content related to beauty products account for more than 75% of all advertisement contents can be selected as candidate influencers, and 'A' influencers It is possible to obtain the advertisement information of the influencer and the advertisement information of the 'C' influencer.

In step S207, the device 200 may obtain information about advertisement content performed by the candidate influencer based on the advertisement information of the candidate influencer.

In detail, the device 200 includes the number of advertisement contents of the candidate influencer, the category of the advertisement contents of the candidate influencer, the number of views of the advertisement contents of the candidate influencer, and comments based on the advertisement information of the candidate influencer. Information on advertisement contents performed by candidate influencers, including the number of shares and the number of shares, may be obtained.

In step S208, the device 200 performs an advertisement for a first product among the candidate influencers based on the advertisement information of the candidate influencer, the advertisement content information performed by the candidate influencer, and the first product information. You can choose an influencer to do it.

Specifically, the device 200 obtains target information of the candidate influencer based on the advertisement information of the candidate influencer, and based on the advertisement content information performed by the candidate influencer, the candidate influencer Content interest information is obtained, target information of the candidate influencer, content interest information of the candidate influencer, and information of the first product are applied to the first artificial neural network to select an influencer to advertise the first product. can do. A detailed description in this regard will be made with reference to FIG. 4 .

3 is a flowchart illustrating a process of matching a beauty product manufacturer and a brand maker through performance results of the beauty product manufacturer according to an embodiment.

Referring to FIG. 3 , in step S301 , the device 200 may obtain the number of second products of a beauty product manufacturer. In this case, the number of second products is not the number of products manufactured, but the number of products corresponding to the first product, and through this, it is possible to check how many products related to the first product have been manufactured by the manufacturer.

Specifically, the device 200 may identify the manufacturer of the second product based on information on the second product, and obtain the number of second products corresponding to the beauty product manufacturer.

For example, 'A' beauty product, 'D' beauty product, 'E' beauty product, 'F' beauty product, 'G' beauty product, and 'H' beauty product manufactured by 'A' beauty product manufacturer as second products. There are beauty products, 'I' beauty products, 'J' beauty products, 'ㄱ' beauty products manufactured by 'ㄱ' beauty product manufacturers, 'ㄴ' beauty products, 'ㄴ' beauty products, 'ㄹ' beauty products, When there is 'ㅁ' beauty product, the device 200 may obtain 8 as the number of second products of 'A' beauty product manufacturer, and obtain 5 as the number of second products of 'A' beauty product manufacturer. can do.

In step S302, the device 200 may generate a beauty product manufacturer's trust index based on the number of second products.

For example, when the number of second products of beauty product manufacturer 'A' is 8 and the number of second products of beauty product manufacturer 'A' is 5, the device 200 determines the reliability of beauty product manufacturer 'A'. The index can be created as 80, and the trust index of the 'a' beauty product manufacturer can be created as 50.

In this case, the maximum score of the trust index may vary according to the embodiment, and the trust index may be generated in proportion to the preset maximum number of second products. For example, if the preset maximum number of second products is 10 and the maximum score of the trust index is 100, if the number of second products is 10 or more, the trust index can be generated as 100 points, and the second If the number of products is 10 or less, a trust index may be generated with a value proportional to (the number of second products/10).

In operation S303 , the device 200 may classify, among the second products, products whose actual sales volume is greater than a predefined expected sales volume, into the first group, based on the second product information.

In detail, the device 200 may obtain actual sales volume and expected sales volume of the second product based on information on the second product, and classify products whose actual sales volume is greater than the predicted sales volume into the first group.

In operation S304 , the device 200 may classify, among the second products, products whose actual sales volume is smaller than a predefined expected sales volume among the second products, based on the information on the second products, into the second group.

In detail, the device 200 may obtain actual sales volume and expected sales volume of the second product based on information on the second product, and classify products whose actual sales volume is smaller than the predicted sales volume into the second group.

In step S305, the device 200 may generate a first number that is the number of products classified into the first group.

For example, in the case of 'A' beauty products, 'D' beauty products, 'E' beauty products, 'F' beauty products, 'G' beauty products, and 'H' beauty products manufactured by the 'A' beauty product manufacturer , If the actual sales volume is greater than the expected sales volume and the actual sales volume is less than the expected sales volume in the case of 'I' beauty products and 'J' beauty products, the device 200 may generate six as the first number.

In step S306, the device 200 may generate a second number that is the number of products classified into the second group.

For example, in the case of 'A' beauty products, 'D' beauty products, 'E' beauty products, 'F' beauty products, 'G' beauty products, and 'H' beauty products manufactured by the 'A' beauty product manufacturer , If the actual sales volume is greater than the expected sales volume and the actual sales volume is smaller than the expected sales volume in the case of 'I' beauty products and 'J' beauty products, the device 200 may generate two as the second number.

In step S307, the device 200 may generate a third number as a sum of the first number and the second number.

For example, when the first number is 6 and the second number is 2, the device 200 may generate 8 as the third number.

In step S308, the device 200 may generate a recommendation index of a beauty product manufacturer based on a value obtained by dividing the first number by the third number. In this case, the maximum value of the recommendation index may vary according to embodiments.

For example, when the first number of 'A' beauty product manufacturers is 6 and the third number is 8, and the first number of 'A' beauty product manufacturers is 4 and the third number is 5, the device 200 A recommendation index of 'A' beauty product manufacturer may be generated as 75, and a recommendation index of 'A' beauty product manufacturer may be generated as 80.

In step S309, the apparatus 200 may generate a beauty product manufacturer's score based on the beauty product manufacturer's trust index and the beauty product manufacturer's recommendation index.

For example, if the reliability index of the beauty product manufacturer 'A' is 80 and the recommendation index is 75, and the trust index of the beauty product manufacturer 'A' is 50 and the recommendation index is 80, the device 200 may use the 'A' beauty product manufacturer's reliability index. The product manufacturer's score can be generated as 155, and the 'A' beauty product manufacturer's score can be generated as 130.

In step S310, the device 200 may match the brand maker with the beauty product manufacturer based on the score of the beauty product manufacturer.

For example, if the score of the 'A' beauty product manufacturer is 155 and the score of the 'A' beauty product manufacturer is 130, the device 200 may match the brand maker with the 'A' beauty product manufacturer. .

Also, according to an embodiment, the highest scores of the trust index and the recommendation index may be set to be the same, but the highest scores may be set differently for each point that the user considers important. For example, the highest score of the trust index and the recommendation index may all be the same at 100 points, and if the user values the number of performance experiences, the highest score of the trust index is 150 points and the highest score of the recommendation index is 100. It may be points, or for users who value performance performance, that is, whether actual sales volume exceeds expected sales volume, the highest score of recommendation index is 150 points, and the highest score of trust index may be 100 points.

FIG. 4 is a diagram for explaining a process of selecting an influencer to advertise a product based on information on candidate influencers according to an embodiment.

Referring to FIG. 4 , first, in step S401, the apparatus 200 performs target information of the candidate influencer including target age information and target gender information of the candidate influencer based on the advertisement information of the candidate influencer. can be obtained.

Specifically, the device 200 may obtain follower information of the candidate influencer based on advertisement information of the candidate influencer, analyze the follower information of the candidate influencer, and analyze the target age group of the candidate influencer. Are they in their teens, 20s, 30s, 40s, 50s, 60s, 70s, or whether the target age of the candidate influencer is a teenager, young adult, middle-aged, mature, etc. , and based on the result of the identification, target age information of the candidate influencer can be obtained. The device 200 may obtain follower information of the candidate influencer based on the advertisement information of the candidate influencer, and analyze the follower information of the candidate influencer to determine whether the target gender of the candidate influencer is female. , it is possible to determine whether a person is male, and based on the identification result, target gender information of the candidate influencer can be obtained. In addition, the device 200 may obtain target information of the candidate influencer including target age information of the candidate influencer and target gender information of the candidate influencer.

In step S402, the device 200 determines the number of advertisement contents, the average number of views of advertisement contents, and the average share of advertisement contents based on the advertisement contents information of the candidate influencer. Content interest information of the candidate influencer including the number of times and the average number of comments on advertisement contents may be obtained.

In step S403, the device 200 may generate a first input signal based on the target information of the candidate influencer, the content interest information of the candidate influencer, and the information of the first product.

Specifically, the device 200 may perform a process of pre-processing the target information of the candidate influencer, the content interest information of the candidate influencer, and the information of the first product. The target information of the preprocessed candidate influencer, the content interest information of the candidate influencer, and the information of the first product are used as inputs to the first artificial neural network, or are input through normal processing to remove unnecessary information. can create

In step S404, the device 200 may generate a first output signal by applying the first input signal to the first artificial neural network.

Here, the device 200 obtains target information of the training influencer, content interest information of the training influencer, information of a training beauty product, first output signals, and training influencer matching information, and thus Based on this, the first artificial neural network may be trained in advance. The apparatus 200 may generate a first output signal by applying a first input signal to a first artificial neural network that has been trained in advance. In this case, the training influencer matching information may be influencer matching information corresponding to the training influencer's target information, the training influencer's content interest information, and the training beauty product information. The first output signals are generated by applying the first training input signals generated based on the training influencer's target information, the training influencer's content interest information, and the training beauty product information to the first artificial neural network. can be output signals

According to an embodiment, the apparatus 200 may obtain training outputs by applying target information of the training influencer, content interest information of the training influencer, and training beauty product information to the first artificial neural network. . Apparatus 200 may train a first artificial neural network based on the training outputs, the first output signals, and the training influencer matching information. The apparatus 200 may generate a first output signal by applying a first input signal to a first artificial neural network that has been trained in advance.

Apparatus 200 may train a first artificial neural network based on the training outputs, the first output signals, and the training influencer matching information. The apparatus 200 may train the first artificial neural network by calculating training errors corresponding to the training outputs and optimizing a connection relationship of nodes in the first artificial neural network to minimize the training errors. The device 200 may extract influencer matching information from the influencer's target information, the influencer's content interest information, and the first product information by using the first artificial neural network for which learning has been completed.

The device 200 may train the first artificial neural network to extract influencer matching information.

The first artificial neural network may include a first input layer into which training samples are input and a first output layer including training outputs, and may be learned based on differences between the training outputs and labels. Here, the labels may be defined based on target information of the influencer, content interest information of the influencer, and information of the first product. The first artificial neural network is connected to a group of a plurality of nodes, and is defined by weights between the connected nodes and an activation function for activating the nodes.

The apparatus 200 may train the first artificial neural network using a gradient descent (GD) technique or a stochastic gradient descent (SGD) technique. The device 200 may use a loss function designed by outputs and labels of the first artificial neural network.

Apparatus 200 may calculate the training error using a predefined loss function. The loss function may be predefined with labels, outputs, and parameters as input variables, where the parameters may be set by weights in the first artificial neural network. For example, the loss function may be designed in a mean square error (MSE) form, an entropy form, and the like, and various techniques or methods may be employed in an embodiment in which the loss function is designed.

The apparatus 200 may find weights affecting the training error using a backpropagation technique. Here, weights are relations between nodes in the first artificial neural network. Apparatus 200 may use the SGD technique using labels and outputs to optimize the weights found through the backpropagation technique. For example, the apparatus 200 may update weights of a loss function defined based on labels, outputs, and weights using the SGD technique.

According to an embodiment, the apparatus 200 may generate first training input signals based on target information of the training influencer, content interest information of the training influencer, and training product information. Apparatus 200 may generate first output signals from first training input signals.

According to an embodiment, the first artificial neural network is based on target information of the training influencer, content interest information of the training influencer, training product information, first output signals, and training influencer matching information. can be learned in advance. The first artificial neural network may be learned by minimizing training errors generated based on differences between the first output signals and the training influencer matching information.

In step S405, the device 200 may generate matching information corresponding to the first product and the candidate influencer based on the first output signal. Here, the influencer matching information is a degree of matching between the candidate influencer and the first product, and may be a real value between 0 and 1.

For example, the device 200 sets 0.8 as influencer matching information corresponding to 'A' influencer and 0.3 as influencer matching information corresponding to 'C' influencer through the first artificial neural network. It is possible to generate 0.5 as influencer matching information corresponding to D' influencer and 0.6 as influencer matching information corresponding to 'E' influencer.

In step S406, the device 200 may check a history of advertising products produced by matched beauty product manufacturers among candidate influencers and apply a weight proportional to the number of advertisements to the matching information.

For example, the candidate influencers are 'A' influencer, 'C' influencer, 'D' influencer, and 'E' influencer, and products produced by the matched 'A' beauty product manufacturer If the number of advertisements is 2 times for 'A' influencer, 3 times for 'C' influencer, 3 times for 'D' influencer, and 1 time for 'E' influencer, the device (200) can apply 0.2 as a weight proportional to the number of advertisements to 'A' influencer, apply 0.3 as a weight proportional to the number of advertisements to 'C' influencer, and apply 'D' influencer as a weight proportional to the number of advertisements. 0.3 can be applied to the influencer as a weight proportional to the number of advertisements, and 0.1 can be applied to the 'E' influencer as a weight proportional to the number of advertisements.

In step S407, the device 200 may select an influencer to advertise the first product by using the weighted matching information.

For example, the influencer matching information corresponding to 'A' influencer is 0.8, the weight proportional to the number of advertisements is 0.2, and the influencer matching information corresponding to 'C' influencer is 0.3, the number of advertisements The weight proportional to is 0.3, the influencer matching information corresponding to the 'D' influencer is 0.5, the weight proportional to the number of advertisements is 0.3, and the influencer matching information corresponding to the 'E' influencer is 0.6, when the weight proportional to the number of advertisements is 0.1, the device 200 generates matching information with a weight corresponding to 'A' influencer as 1, and a weight corresponding to 'C' influencer is applied. First product by generating matching information as 0.6, weighted matching information corresponding to the 'D' influencer as 0.8, and weighted matching information corresponding to the 'E' influencer as 0.7. 'A' influencer can be selected as the influencer to carry out the advertisement.

5 is a flowchart illustrating a process of determining an advertisement contribution when a selected influencer performs an advertisement according to an embodiment.

Referring to FIG. 5 , first, in step S501, the device 200 acquires the release time of the first product, the upload time of the advertisement content of the first product, and the posting maintenance period of the first product to the brand maker terminal, and the acquired information is selected. It can be transmitted to the influencer's terminal 400. Here, the acquired information may include a release time of the first product, an upload time of advertising content of the first product, and a posting maintenance period.

Specifically, the device 200 may acquire the release time of the first product, the upload time of the advertisement content of the first product, and the posting maintenance period from the brand maker terminal, and obtain the obtained release time of the first product and the first product. The upload time and posting maintenance period of the advertisement content may be matched with the first product and stored in the database. In addition, the device 200 may transmit the release time of the first product, the upload time of the advertisement content of the first product, and the posting maintenance period to the terminal 400 of the selected influencer.

In step S502 , the device 200 may generate a first period from the time the first product is released to the time advertisement content of the first product is uploaded.

That is, the device 200 may check the time from the release of the first product to the time of uploading the advertising content of the first product through the information obtained from the brand maker terminal, and the advertisement of the first product from the time of release of the first product. Up to the time of content uploading may be created as the first period.

For example, if the release time of the first product is August 01, 2022 and the upload time of the advertisement content of the first product is August 08, 2022, the device 200 displays the first period as the first period, August 01, 2022. You can create 7 days from 01st to 08/08/2022.

In step S503, the apparatus 200 may generate a first sales volume, which is the sales volume of the first product during the first period, and set a reference range based on the first sales volume.

Specifically, when the uploading of the advertising content for the first product has passed, the device 200 displays the sales volume of the first product during the first period from the release of the first product to the uploading of the advertising content for the first product. 1 sales volume may be generated and a reference range may be set based on the first sales volume. At this time, the ratio for setting the reference range may vary depending on the embodiment, and may be ±10%, ±5%, or other ratios.

For example, the release time of the first product is August 01, 2022, the upload time of the advertisement content of the first product is August 08, 2022, and the time from August 01, 2022 to August 08, 2022 If 50,000 units of the first product have been sold by , and the rate for setting the reference range is ±10%, the device 200 may set the first sales amount, which is the sales amount of the first product during the first period, to 50,000 units, and Based on sales volume, you can set a baseline range of 45,000 to 55,000 units.

In step S504, the device 200 generates a second sales volume, which is the sales volume during the first period from the release of a third product matching the category of the first product among products released by the brand maker, and the second sales volume is within the reference range. It is checked whether the product is within the range, and third products having a second sales volume within a reference range may be classified into groups.

Specifically, the device 200 may obtain information on products released by the brand maker, and extract a third product matching the category of the first product from among products released by the brand maker. The apparatus 200 may generate the second sales amount, which is the sales amount during the first period from the release of the third product. Also, the apparatus 200 may determine whether the second sales volume is within the reference range, and classify third products having the second sales volume within the reference range into groups.

For example, the first product category is hair and body, and the products released by the brand maker are 'Ga' beauty products, 'Me' beauty products, 'Cha' beauty products, 'La' beauty products, and 'Ma' beauty products. 'A' beauty product category is basic cosmetics, 'B' beauty product category is hair and body, 'C' beauty product category is color cosmetics, 'LA' beauty product category is hair and body, ' When the beauty product category of 'Ma' is hair and body and the first period is 7 days, the device 200 selects 'me' whose category matches the hair and body category of the first product among products released by the brand maker. Beauty product, 'La' beauty product, and 'Ma' beauty product can be extracted as a third product, and the second sales volume of 'My' beauty product, which is the sales volume for 7 days from the release of 'I' beauty product, is obtained and can acquire and generate a second sales volume of 'La' beauty product, which is the sales volume for 7 days from the release of 'La' beauty product, and for 7 days from the release of 'E' beauty product A second sales volume of 'E' beauty products, which is the sales volume of 'E', may be acquired and generated.

In addition, if the reference range is 45,000 to 55,000, the second sales volume of 'I' beauty products is 48,000 units, the second sales volume of 'D' beauty products is 30,000 units, and the second sales volume of 'E' beauty products is 53,000 units, The device 200 may determine that the second sales volume of 'I' beauty product and the second sales volume of 'E' beauty product are within the reference range, and classify 'I' beauty product and 'E' beauty product into groups. .

In step S505, the device 200 may generate a second period from the release of the first product to the time when a preset period elapses after uploading the advertising content of the first product. Here, the preset period is a point in time when the posting maintenance period has elapsed and may vary according to embodiments.

In detail, the device 200 may generate a second period from the release of the first product to the time when the advertisement content of the first product has passed after the advertisement content of the first product has been uploaded.

For example, the release time of the first product is August 01, 2022, the upload time of the advertisement content of the first product is August 08, 2022, and the posting maintenance period of the advertisement content of the first product is 2022. If it is from August 08 to August 15, 2022, the device 200 displays the date of release of the first product on August 08, 2022, when the maintenance period of the advertising content of the first product has elapsed from August 01, 2022. The 28th of the 29th of the month can be created as the second period.

In step S506, the apparatus 200 may generate a first total sales amount, which is the total sales amount of the first product during the second period.

For example, if the release date of the first product is August 01, 2022 and the second period is 28 days, the device 200 may use the first product from August 01, 2022 to August 29, 2022. The sales volume can be obtained, and 1,500,000, which is the total sales volume of the first product for 28 days, can be obtained.

In step S507 , the apparatus 200 may generate a second total sales amount by calculating an average value sold during the second period from the release time of the third product included in the group.

In addition, as a result of checking the sales volume of 'I' beauty products included in the group for 28 days from the launch of 'My' beauty products, the sales volume was 800,000 units, and 'Ma' beauty products of 'Ma' beauty products As a result of checking the sales volume of the 'Ma' beauty product for 28 days from the time of release, if the sales volume is 1,000,000 units, the device 200 calculates an average value of 800,000 units and 1,000,000 units to generate a second total sales volume of 900,000 units.

In step S508, the device 200 may determine whether the first total sales volume is greater than the second total sales volume.

If it is determined in step S508 that the first total sales volume is greater than the second total sales volume, in step S509, the device 200 may determine that the influencer has a contribution to the advertising of the first product.

For example, if the total sales volume of the first product is 1,500,000 units and the total sales volume of the second unit is 900,000 units, the device 200 determines that the total sales volume of the first product is greater than the total sales volume of the second product, and the first product through the influencer. It can be judged that there is an advertising contribution of

If it is determined in step S508 that the first total sales volume is not greater than the second total sales volume, in step S510, the device 200 determines that the advertising contribution of the first product through the influencer is insufficient, and the advertisement content of the first product is determined. and monitoring the sales volume of the first product, and generating a report for the monitoring.

For example, when the total sales volume of the first product is 1,500,000 units and the second total sales volume is 2,000,000 units, the device 200 determines that the first total sales volume is not greater than the second total sales volume, and displays the advertisement content for the first product. The number of views, the number of comments, the number of shares, and the sales volume of the first product may be monitored, and a report for the monitoring may be generated.

6 is a flowchart illustrating a process of providing product information to a selected influencer according to an embodiment.

Referring to FIG. 6 , first, in step S601, the device 200 may obtain information on all contents uploaded by the selected influencer. Here, the content information may include whether or not advertising content is included, the number of views of the content, a running time of the content, and a running time of the advertising content when the advertising content is included.

That is, the device 200 may obtain information on all content uploaded by a selected influencer through a database including at least one YouTube or blog.

For example, if the selected influencer is an 'A' influencer, the device 200 may obtain information on all contents uploaded by the 'A' influencer through the YouTube database.

In step S602, the device 200 may classify content including advertising content among all content uploaded by the selected influencer as a first meeting.

For example, the selected influencer is an 'A' influencer, and the entire content uploaded by the 'A' influencer includes the first content including 'A' advertisement content, and the 'D' advertisement content. In the case of the second content, the third content not including advertising content, the fourth content not including advertising content, and the fifth content not including advertising content, the device 200 displays the first content including advertising content; The second content may be classified as the first group.

In step S603, the device 200 may classify content that does not include advertising content among all content uploaded by the selected influencer as a second meeting.

For example, the selected influencer is an 'A' influencer, and the entire content uploaded by the 'A' influencer includes the first content including 'A' advertisement content, and the 'D' advertisement content. In the case of the second content, the third content not including advertising content, the fourth content not including advertising content, and the fifth content not including advertising content, the device 200 displays the third content not including advertising content. , the fourth content and the fifth content can be classified as the second group.

In step S604 , the device 200 may obtain advertising content running times corresponding to the content included in the first meeting, calculate an average value of the advertising content running times, and generate the first time.

Specifically, the device 200 may obtain advertising content running times corresponding to content included in a first group, which is a group of content including advertising content, and calculate an average value of the advertising content running times for the first time period. can be created with

For example, when first content including 'A' advertisement content and second content including 'D' advertisement content are a first meeting, the device 200 presents 'A' advertisement content of the first content. The time and running time of 'D' advertising content of the second content may be acquired. In addition, when the running time of 'A' advertisement content is 8 minutes and the running time of 'D' advertisement content is 12 minutes, the device 200 may generate 10 minutes as the first time.

In step S605, the device 200 may generate a first average number of views by analyzing the number of views corresponding to the content included in the first meeting.

For example, the first content including 'A' advertisement content, the second content including 'D' advertisement content are the first group, the number of views of the first content including 'A' advertisement content is 110,000, When the number of views of the second content including the 'D' advertising content is 90,000, the device 200 may generate 100,000 as the first average number of views.

In step S606, the device 200 may generate a second average number of views by analyzing the number of views corresponding to the content included in the second meeting.

For example, the third content not including advertising content, the fourth content not including advertising content, and the fifth content not including advertising content are the second meeting, the number of views of the third content is 200,000, and the fourth When the number of views of the content is 170,000 and the number of views of the fourth content is 230,000, the device 200 may generate 200,000 as the second average number of views.

In step S607, the device 200 may generate a first ratio by dividing the first average number of views by the second average number of views.

For example, when the first average number of hits is 100,000 and the second average number of hits is 200,000, the device 200 may generate 0.5 as the first ratio.

In step S608, the device 200 may determine whether the first ratio is greater than 1.

If it is determined that the first ratio is greater than 1 in step S608, in step S609, the device 200 generates advertisement content for the first product for a second time period longer than the first time, and the terminal 400 of the selected influencer ) can be provided.

For example, when the first average number of views is 250,000, the second average number of views is 200,000, the first time is 10 minutes, and the second time is 15 minutes, the device 200 generates the first ratio as 1.5 and the first If it is determined that the ratio is greater than 1, advertisement content for the first product may be generated for a second time period of 15 minutes and provided to the terminal 400 of the selected influencer.

If it is determined in step S608 that the first ratio is not greater than 1, in step S610, the device 200 may determine whether the first ratio is greater than a predefined first reference ratio. Here, the first reference ratio may vary according to embodiments as a preset ratio.

For example, when the first average number of hits is 100,000 and the second average number of hits is 200,000, the device 200 generates a first ratio of 0.5, determines that the first ratio is smaller than 1, and determines that the first ratio is predefined. It may be determined whether the ratio is greater than the first reference ratio.

If it is determined in step S610 that the first ratio is greater than the first reference ratio, in step S611, the device 200 generates advertising content for the first product for a first amount of time and sends it to the terminal 400 of the selected influencer. can provide

For example, when the first average number of views is 150,000, the second average number of views is 200,000, the first reference rate is 0.7, and the first time period is 10 minutes, the device 200 generates the first rate as 0.75 and the first rate is 0.75. By determining that the ratio is less than 1 and greater than the first standard ratio of 0.7, advertisement content for the first product may be generated for the first time of 10 minutes and provided to the terminal 400 of the selected influencer.

If it is determined in step S610 that the first ratio is not greater than the first reference ratio, in step S612, the device 200 generates advertising content for the first product for a third time shorter than the first time, and selects the influencer. of can be provided to the terminal 400.

For example, when the first average number of views is 100,000, the second average number of views is 200,000, the first reference rate is 0.7, the first time is 10 minutes, and the third time is 7 minutes, the device 200 sets the first rate is 0.5, the first ratio is smaller than 1, and the first reference ratio is smaller than 0.7, and the advertisement content for the first product is generated for a third time, 7 minutes, and the selected influencer's terminal 400 can be provided with

7 is a flowchart illustrating a process of replacing an image including an influencer with a product image on a sales page according to an embodiment.

Referring to FIG. 7 , first, in step S701, the device 200 can confirm that advertising content has been uploaded to a video sharing site.

In step S702, the device 200 may extract a video image of a first view from the advertising content as a first image. That is, the device 200 may capture an image of the first viewpoint from the advertising content and extract the captured image as the first image. Here, the first viewpoint may be set differently according to embodiments.

In step S703, the device 200 may classify an area occupied by a product in the first image as a first area.

Specifically, the device 200 may analyze the first image, recognize the first product on the first image, and determine the location of the first product positioned at the far left on the first image as the first location. and confirms the position of the first product located at the top on the first image as the second position, confirms the position of the first product located on the far right on the first image as the third position, and on the first image The position of the first product located at the lowest side can be identified as the fourth position.

Thereafter, the device 200 generates a first straight line that extends in the vertical direction based on the first position, generates a second straight line that extends in the left and right direction based on the second position, and creates a vertical and horizontal line based on the third position. A third straight line extending in a direction may be generated, and a fourth straight line extending in a left-right direction based on the fourth position may be generated.

Thereafter, the device 200 may set an area connecting the first straight line, the second straight line, the third straight line, and the fourth straight line as the first area, and then distinguish the first area from the first image.

In step S704, the device 200 may divide the first image into the first region and extract the divided image as the 1-1 image.

In step S705, the device 200 may check whether it is recognized that there is an influencer in the 1-1 image. That is, the device 200 may determine whether an influencer exists in the image 1-1 by checking whether an object in the form of a person other than letters is recognized on the image 1-1.

If it is confirmed in step S705 that there is an influencer in the 1-1 image, in step S706, the device 200 may divide the area occupied by the influencer in the 1-1 image as a second area. In this case, the device 200 may divide the second region from the 1-1 image in the same way as the first region from the first image.

In step S707, the device 200 may reproduce and analyze advertisement content in reverse chronological order from the first point of view.

In step S708, the apparatus 200 may confirm that there is no influencer in the second area at the second time point as a result of reproducing and analyzing the advertising content in reverse chronological order from the first time point.

That is, the device 200 can monitor the reverse movement of the influencer in the second area by playing the advertising content in reverse order in time from the first point of view, and the influencer in the second area can monitor the movement of the influencer in the second area. A time point at which it is confirmed that the object is out of order may be set as the second time point.

In step S709, the device 200 may extract a video image of a second viewpoint from the advertising content as a second image. That is, the device 200 may capture an image of the second viewpoint from the advertising content and extract the captured image as the second image.

In step S710, the device 200 may extract the 2-1 image by dividing the second region in the second image.

In step S711, the device 200 may replace a portion of the 1-1 image with the second area with the 2-1 image.

Specifically, if it is confirmed that there is an influencer in the 1-1 image, the device 200 may classify an area occupied by the influencer in the 1-1 image as a second area, and The 1-1 image in which the 1-1 image and the 2-1 image are combined may be generated by deleting a portion of the second area and inserting the 2-1 image at the deleted position. In other words, the part with the second area in the 1-1 image is replaced with the 2-1 image, the influencer that was in the 1-1 image is deleted, and the part without the influencer is added in the deleted position. As a result, the influencer may no longer be recognized in the 1-1 image.

8 is an exemplary diagram of a configuration of a device according to an embodiment.

Device 200 according to an embodiment includes a processor 210 and a memory 220 . The processor 210 may include at least one device described above with reference to FIGS. 1 to 7 or may perform at least one method described above with reference to FIGS. 1 to 7 . Individuals or organizations using the device 200 may provide services related to some or all of the methods described above with reference to FIGS. 1 to 7 .

The memory 220 may store information related to the methods described above or may store a program in which the methods described below are implemented. Memory 220 may be volatile memory or non-volatile memory.

The processor 210 may execute a program and control the device 200 . Program codes executed by the processor 210 may be stored in the memory 220 . The device 200 may be connected to an external device (eg, a personal computer or network) through an input/output device (not shown) and exchange data through wired/wireless communication.

Apparatus 200 may be used to train an artificial neural network or to use a trained artificial neural network. The memory 220 may include a learning or learned artificial neural network. The processor 210 may learn or execute an artificial neural network algorithm stored in the memory 220 . The device 200 for learning the artificial neural network and the device 200 using the learned artificial neural network may be the same or separate.

The embodiments described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (3)

In the beauty product manufacturer matching method using artificial intelligence-based influencer information and brand maker information, performed by a device,
acquiring information on a first product, which is a beauty product to be developed, and a proposal for the first product, from a brand maker terminal;
obtaining a category of the first product based on the information of the first product;
acquiring, from a database, information on a second product among products manufactured by the beauty product manufacturer, the sales quantity of which is equal to or greater than a reference value, and which is a beauty product whose category is the same as that of the first product;
performing matching between the brand maker and the beauty product manufacturer based on the second product information;
Obtaining advertising content performed by an influencer from at least one database;
Obtaining advertisement information of a candidate influencer whose ratio of advertisement contents related to beauty products among all advertisement contents is equal to or greater than a preset reference ratio, based on the advertisement contents performed by the influencer;
obtaining advertisement content information performed by the candidate influencer based on the advertisement information of the candidate influencer; and
Based on the advertisement information of the candidate influencer, the advertisement content information performed by the candidate influencer, and the information of the first product, the influencer who will perform the advertisement of the first product among the candidate influencers Including the step of selecting a
The step of performing matching between the brand maker and the beauty product manufacturer based on the information of the second product,
acquiring the number of the second products of the beauty product manufacturer;
generating a trust index of the beauty product manufacturer based on the number of the second products;
Based on the information on the second product, products whose actual sales volume is greater than a predefined expected sales volume among the second products are classified into a first group, and the actual sales volume of the product among the second products is the expected sales volume. classifying products that are no larger than a second population;
generating a first number that is the number of products classified into the first group;
generating a second number that is the number of products classified into the second group;
generating a third number that is a sum of the first number and the second number;
generating a recommendation index of the beauty product manufacturer based on a value obtained by dividing the first number by the third number;
generating a score of the beauty product manufacturer based on a trust index of the beauty product manufacturer and a recommendation index of the beauty product manufacturer; and
Performing matching between the brand maker and the beauty product manufacturer based on the scores of the beauty product manufacturer;
Beauty product manufacturer matching method using AI-based influencer information and brand maker information. delete According to claim 1,
The step of selecting an influencer to perform an advertisement for the first product from among the candidate influencers,
obtaining target information of the candidate influencer including target age information and target gender information of the candidate influencer based on the information of the candidate influencer;
The candidate influencer including the number of advertisement contents, the average number of views of the advertisement contents, the average number of advertisement sharing of the contents, and the average number of comments on the advertisement contents, based on the advertisement contents information of the candidate influencer. obtaining content interest information of;
generating a first input signal based on target information of the candidate influencer, content interest information of the candidate influencer, and information of the first product;
generating a first output signal by applying the first input signal to a first artificial neural network;
generating matching information corresponding to the first product and the candidate influencer based on the first output signal;
checking a history of advertising products produced by a matched beauty product manufacturer among the candidate influencers and applying a weight proportional to the number of advertisements to the matching information; and
Selecting an influencer to advertise the first product using the matching information to which the weight is applied;
Beauty product manufacturer matching method using AI-based influencer information and brand maker information.

Images